Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    probability calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уется
    -0.06
     وذلك
    -0.06
    amiliar
    -0.06
     редак
    -0.06
    .Circle
    -0.06
    정보
    -0.06
    .range
    -0.06
    .ADD
    -0.06
    marked
    -0.06
    .setVertical
    -0.06
    POSITIVE LOGITS
    ilestone
    0.07
     currentNode
    0.07
     będ
    0.07
    before
    0.07
     makes
    0.06
     impacting
    0.06
     Train
    0.06
    _private
    0.06
    cos
    0.06
     П
    0.06
    Act Density 0.004%

    No Known Activations